# leak-triage-and-validation

The leak-triage-and-validation Claude Code skill sorts leaked tokens, keys, and repositories. It checks credentials and their value, then prepares findings for responsible disclosure.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 326 repo stars
- Author: mrhlaingbwardev
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mrhlaingbwardev/agentic-hacking-skills/tree/HEAD/skills/leak-triage-and-validation/SKILL.md
- Updated: 2026-11-01
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/leak-triage-and-validation

## What it does

The skill filters a noisy leak into findings that pass validation and merit a report. It classifies candidate secrets, removes duplicates, checks account identity and permissions with read-only requests, then scores findings by value and ROI.

Raw artifacts stay in an isolated vault on the VPS. The model sees only metadata from `triage.json`, never the secret values. Candidate extraction can use `gitleaks`, `TruffleHog`, or regular expressions with entropy checks.

The skill profiles the owner and hands the finding and profile to `disclosure-communication` or an equivalent skill. It drafts a redacted report and outreach message; a person must approve anything sent. Contacts and follow-up outcomes go into a tracker. Credentials must not be used to access accounts, and checks must not write data.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/leak-triage-and-validation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/leak-triage-and-validation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/leak-triage-and-validation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/leak-triage-and-validation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mrhlaingbwardev/agentic-hacking-skills skills/leak-triage-and-validation
```

2. **Manually: put the files in place**
- File: `.github/skills/leak-triage-and-validation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mrhlaingbwardev/agentic-hacking-skills --path skills/leak-triage-and-validation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/leak-triage-and-validation/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mrhlaingbwardev/agentic-hacking-skills/tree/HEAD/skills/leak-triage-and-validation/SKILL.md

## When to use it
- deduplicate credentials found in a leak
- check whether a key is live and what permissions it has
- rank findings by value and ROI
- draft a redacted disclosure report for human approval
- track contacts and disclosure outcomes

## Example prompts
- Sort this leak, check credentials with read-only requests, and rank findings by ROI.
- Review metadata for this private repository and decide what belongs in a report.
- Profile the owner and prepare the finding for `disclosure-communication`; do not send a message.

## Similar
- [hunt-source-leak](https://affpapa.org/en/nevibecode/skills/hunt-source-leak.md) — skill · ★ 16193 repo stars
- [dependency-vulnerability-triage](https://affpapa.org/en/nevibecode/skills/dependency-vulnerability-triage.md) — skill · 296 installs
- [triage-validation](https://affpapa.org/en/nevibecode/skills/triage-validation.md) — skill · ★ 16193 repo stars
- [ci-triage](https://affpapa.org/en/nevibecode/skills/ci-triage.md) — skill · ★ 11819 repo stars
- [triage-vulnerabilities](https://affpapa.org/en/nevibecode/skills/triage-vulnerabilities.md) — skill · ★ 720 repo stars
- [post-patch-validation](https://affpapa.org/en/nevibecode/skills/post-patch-validation.md) — skill · 1400 installs

From the same set: [mrhlaingbwardev/agentic-hacking-skills](https://affpapa.org/en/nevibecode/by/mrhlaingbwardev/agentic-hacking-skills.md) — 28 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
